FIX: first_seen re-stamp bug — persist true source publish date, idempotent upsert, backfill DB

adapters/arxiv.py

@@ -33,6 +33,7 @@ from datetime import datetime, timedelta, timezone
 from html import unescape
 
 from adapters import SourceAdapter
+from adapters._store import true_first_seen, upsert_entries
 
 # arXiv API
 ARXIV_API = "http://export.arxiv.org/api/query"
@@ -443,6 +444,7 @@ class ArxivAdapter(SourceAdapter):
                 raw_meta["applied_domain"] = paper["_applied_domain"]
 
             now_str = now.strftime("%Y-%m-%dT%H:%M:%SZ")
+            first_seen = true_first_seen(raw_meta, "arxiv", now_str)
             entries.append({
                 "source": "arxiv",
                 "source_id": source_id,
@@ -453,7 +455,7 @@ class ArxivAdapter(SourceAdapter):
                 "category_tags": json.dumps(tags),
                 "signal_score": score,
                 "raw_metadata": json.dumps(raw_meta),
-                "first_seen": now_str,
+                "first_seen": first_seen,
                 "last_updated": now_str,
             })
 
@@ -491,24 +493,7 @@ if __name__ == "__main__":
             conn.commit()
 
         cur = conn.cursor()
-        stored = 0
-        for entry in entries:
-            try:
-                cur.execute("""
-                    INSERT OR REPLACE INTO entries
-                    (source, source_id, url, title, extracted_text, summary,
-                     category_tags, signal_score, raw_metadata, first_seen, last_updated)
-                    VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
-                """, (
-                    entry["source"], entry["source_id"], entry["url"], entry["title"],
-                    entry["extracted_text"], entry["summary"],
-                    entry["category_tags"], entry["signal_score"],
-                    entry["raw_metadata"], entry["first_seen"], entry["last_updated"],
-                ))
-                stored += 1
-            except Exception as e:
-                print(f"  DB error: {e}")
-
+        stored = upsert_entries(conn, entries)
         conn.commit()
         conn.close()
         print(f"  Stored {stored} entries")